© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22889
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    壤
    -0.10
    ovas
    -0.07
    ç§ij夫
    -0.07
    ุม
    -0.07
    æ³½
    -0.07
    å¾Ħ
    -0.07
     à¹Ħ
    -0.07
    ovation
    -0.07
    è¡¢
    -0.07
    åıĹæĥł
    -0.07
    POSITIVE LOGITS
    ä¸ĩäºĭ
    0.07
    èµ°åIJij
    0.07
    ILER
    0.07
    _extension
    0.07
    ott
    0.06
    请注æĦı
    0.06
    astro
    0.06
    æĵĭ
    0.06
    iod
    0.06
    çŁ¥æĻĵ
    0.06
    Activations Density 0.000%

    No Known Activations